Merge tag 'drm-fixes-2023-02-10' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly fixes.

  The amdgpu had a few small fixes to display flicker on certain
  configurations, however it was found the the flicker was lessened but
  there were other unintended consequences, so for now they've been
  reverted and replaced with an option for users to test with so future
  fixes can be developed.

  Otherwise apart from the usual bunch of i915 and amdgpu, there's a
  client, virtio-gpu and an nvidiafb fix that reorders its loading to
  avoid failure.

  client:
   - refcount fix

  amdgpu:
   - a bunch of attempted flicker fixes that regressed turned into a
     user workaround option for now
   - Properly fix S/G display with AGP aperture enabled
   - Fix cursor offset with 180 rotation
   - SMU13 fixes
   - Use TGID for GPUVM traces
   - Fix oops on in fence error path
   - Don't run IB tests on hw rings when sw rings are in use
   - memory leak fix

  i915:
   - Display watermark fix
   - fbdev fix for PSR, FBC, DRRS
   - Move fd_install after last use of fence
   - Initialize the obj flags for shmem objects
   - Fix VBT DSI DVO port handling

  virtio-gpu:
   - fence fix

  nvidiafb:
   - regression fix for driver load when no hw supported"

* tag 'drm-fixes-2023-02-10' of git://anongit.freedesktop.org/drm/drm: (27 commits)
  Revert "drm/amd/display: disable S/G display on DCN 3.1.5"
  Revert "drm/amd/display: disable S/G display on DCN 2.1.0"
  Revert "drm/amd/display: disable S/G display on DCN 3.1.2/3"
  drm/amdgpu: add S/G display parameter
  drm/amdgpu/smu: skip pptable init under sriov
  amd/amdgpu: remove test ib on hw ring
  drm/amdgpu/fence: Fix oops due to non-matching drm_sched init/fini
  drm/amdgpu: Use the TGID for trace_amdgpu_vm_update_ptes
  drm/amdgpu: Add unique_id support for GC 11.0.1/2
  drm/amd/pm: bump SMU 13.0.7 driver_if header version
  drm/amd/pm: bump SMU 13.0.0 driver_if header version
  drm/amd/pm: add SMU 13.0.7 missing GetPptLimit message mapping
  drm/amd/display: fix cursor offset on rotation 180
  drm/amd/amdgpu: enable athub cg 11.0.3
  Revert "drm/amd/display: disable S/G display on DCN 3.1.4"
  drm/amd/display: properly handling AGP aperture in vm setup
  drm/amd/display: disable S/G display on DCN 3.1.2/3
  drm/amd/display: disable S/G display on DCN 2.1.0
  drm/i915: Fix VBT DSI DVO port handling
  drm/client: fix circular reference counting issue
  ...

Author: torvalds

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -243,6 +243,7 @@ extern int amdgpu_num_kcq;
 
 #define AMDGPU_VCNFW_LOG_SIZE (32 * 1024)
 extern int amdgpu_vcnfw_log;
+extern int amdgpu_sg_display;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -1220,10 +1220,13 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
 		 * next job actually sees the results from the previous one
 		 * before we start executing on the same scheduler ring.
 		 */
-		if (!s_fence || s_fence->sched != sched)
+		if (!s_fence || s_fence->sched != sched) {
+			dma_fence_put(fence);
 			continue;
+		}
 
 		r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+		dma_fence_put(fence);
 		if (r)
 			return r;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -186,6 +186,7 @@ int amdgpu_num_kcq = -1;
 int amdgpu_smartshift_bias;
 int amdgpu_use_xgmi_p2p = 1;
 int amdgpu_vcnfw_log;
+int amdgpu_sg_display = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -931,6 +932,16 @@ module_param_named(num_kcq, amdgpu_num_kcq, int, 0444);
 MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = enable)");
 module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444);
 
+/**
+ * DOC: sg_display (int)
+ * Disable S/G (scatter/gather) display (i.e., display from system memory).
+ * This option is only relevant on APUs.  Set this option to 0 to disable
+ * S/G display if you experience flickering or other issues under memory
+ * pressure and report the issue.
+ */
+MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)");
+module_param_named(sg_display, amdgpu_sg_display, int, 0444);
+
 /**
  * DOC: smu_pptable_id (int)
  * Used to override pptable id. id = 0 use VBIOS pptable.

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -618,7 +618,13 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
-		if (!ring->no_scheduler)
+		/*
+		 * Notice we check for sched.ops since there's some
+		 * override on the meaning of sched.ready by amdgpu.
+		 * The natural check would be sched.ready, which is
+		 * set as drm_sched_init() finishes...
+		 */
+		if (ring->sched.ops)
 			drm_sched_fini(&ring->sched);
 
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h

@@ -295,7 +295,7 @@ struct amdgpu_ring {
 #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib)))
 #define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
-#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
+#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0)
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))

drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c

@@ -974,7 +974,7 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params,
 			trace_amdgpu_vm_update_ptes(params, frag_start, upd_end,
 						    min(nptes, 32u), dst, incr,
 						    upd_flags,
-						    vm->task_info.pid,
+						    vm->task_info.tgid,
 						    vm->immediate.fence_context);
 			amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt),
 						   cursor.level, pe_start, dst,

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -6877,7 +6877,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.emit_gds_switch = gfx_v9_0_ring_emit_gds_switch,
 	.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v9_0_ring_test_ring,
-	.test_ib = gfx_v9_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_switch_buffer = gfx_v9_ring_emit_sb,

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -641,7 +641,9 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_GFX_CGLS |
 			AMD_CG_SUPPORT_REPEATER_FGCG |
 			AMD_CG_SUPPORT_GFX_MGCG |
-			AMD_CG_SUPPORT_HDP_SD;
+			AMD_CG_SUPPORT_HDP_SD |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1184,24 +1184,38 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 	memset(pa_config, 0, sizeof(*pa_config));
 
-	logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
-	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
-
-	if (adev->apu_flags & AMD_APU_IS_RAVEN2)
-		/*
-		 * Raven2 has a HW issue that it is unable to use the vram which
-		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
-		 * workaround that increase system aperture high address (add 1)
-		 * to get rid of the VM fault and hardware hang.
-		 */
-		logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18);
-	else
-		logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18;
-
 	agp_base = 0;
 	agp_bot = adev->gmc.agp_start >> 24;
 	agp_top = adev->gmc.agp_end >> 24;
 
+	/* AGP aperture is disabled */
+	if (agp_bot == agp_top) {
+		logical_addr_low  = adev->gmc.vram_start >> 18;
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			/*
+			 * Raven2 has a HW issue that it is unable to use the vram which
+			 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+			 * workaround that increase system aperture high address (add 1)
+			 * to get rid of the VM fault and hardware hang.
+			 */
+			logical_addr_high = (adev->gmc.fb_end >> 18) + 0x1;
+		else
+			logical_addr_high = adev->gmc.vram_end >> 18;
+	} else {
+		logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			/*
+			 * Raven2 has a HW issue that it is unable to use the vram which
+			 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+			 * workaround that increase system aperture high address (add 1)
+			 * to get rid of the VM fault and hardware hang.
+			 */
+			logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18);
+		else
+			logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18;
+	}
+
+	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
 	page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF;
 	page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12);
@@ -1503,6 +1517,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		case IP_VERSION(3, 0, 1):
 		case IP_VERSION(3, 1, 2):
 		case IP_VERSION(3, 1, 3):
+		case IP_VERSION(3, 1, 4):
+		case IP_VERSION(3, 1, 5):
 		case IP_VERSION(3, 1, 6):
 			init_data.flags.gpu_vm_support = true;
 			break;
@@ -1511,6 +1527,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		}
 		break;
 	}
+	if (init_data.flags.gpu_vm_support &&
+	    (amdgpu_sg_display == 0))
+		init_data.flags.gpu_vm_support = false;
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -3626,7 +3626,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 						(int)hubp->curs_attr.width || pos_cpy.x
 						<= (int)hubp->curs_attr.width +
 						pipe_ctx->plane_state->src_rect.x) {
-						pos_cpy.x = temp_x + viewport_width;
+						pos_cpy.x = 2 * viewport_width - temp_x;
 					}
 				}
 			} else {